In settings from fact-checking to question answering, we frequently want to know whether a collection of evidence (premises) entails a hypothesis. Existing methods primarily focus on the end-to-end discriminative version of this task, but less work has treated the generative version in which a model searches over the space of statements entailed by the premises to constructively derive the hypothesis. We propose a system for doing this kind of deductive reasoning in natural language by decomposing the task into separate steps coordinated by a search procedure, producing a tree of intermediate conclusions that faithfully reflects the system's reasoning process. Our experiments on the EntailmentBank dataset (Dalvi et al., 2021) demonstrate that the proposed system can successfully prove true statements while rejecting false ones. Moreover, it produces natural language explanations with a 17% absolute higher step validity than those produced by an end-to-end T5 model.
Language modelling provides a step towards intelligent communication systems by harnessing large repositories of written human knowledge to better predict and understand the world. In this paper, we present an analysis of Transformer-based language model performance across a wide range of model scales -- from models with tens of millions of parameters up to a 280 billion parameter model called Gopher. These models are evaluated on 152 diverse tasks, achieving state-of-the-art performance across the majority. Gains from scale are largest in areas such as reading comprehension, fact-checking, and the identification of toxic language, but logical and mathematical reasoning see less benefit. We provide a holistic analysis of the training dataset and model's behaviour, covering the intersection of model scale with bias and toxicity. Finally we discuss the application of language models to AI safety and the mitigation of downstream harms.
With the proliferation of online misinformation, fake news detection has gained importance in the artificial intelligence community. In this paper, we propose an adversarial benchmark that tests the ability of fake news detectors to reason about real-world facts. We formulate adversarial attacks that target three aspects of "understanding": compositional semantics, lexical relations, and sensitivity to modifiers. We test our benchmark using BERT classifiers fine-tuned on the LIAR arXiv:arch-ive/1705648 and Kaggle Fake-News datasets, and show that both models fail to respond to changes in compositional and lexical meaning. Our results strengthen the need for such models to be used in conjunction with other fact checking methods.
Community Question Answering (CQA) forums provide answers for many real-life questions. Thanks to the large size, these forums are very popular among machine learning researchers. Automatic answer selection, answer ranking, question retrieval, expert finding, and fact-checking are example learning tasks performed using CQA data. In this paper, we present PerCQA, the first Persian dataset for CQA. This dataset contains the questions and answers crawled from the most well-known Persian forum. After data acquisition, we provide rigorous annotation guidelines in an iterative process, and then the annotation of question-answer pairs in SemEvalCQA format. PerCQA contains 989 questions and 21,915 annotated answers. We make PerCQA publicly available to encourage more research in Persian CQA. We also build strong benchmarks for the task of answer selection in PerCQA by using mono- and multi-lingual pre-trained language models
This paper describes our participant system for the multi-modal fact verification (Factify) challenge at AAAI 2022. Despite the recent advance in text based verification techniques and large pre-trained multimodal models cross vision and language, very limited work has been done in applying multimodal techniques to automate fact checking process, particularly considering the increasing prevalence of claims and fake news about images and videos on social media. In our work, the challenge is treated as multimodal entailment task and framed as multi-class classification. Two baseline approaches are proposed and explored including an ensemble model (combining two uni-modal models) and a multi-modal attention network (modeling the interaction between image and text pair from claim and evidence document). We conduct several experiments investigating and benchmarking different SoTA pre-trained transformers and vision models in this work. Our best model is ranked first in leaderboard which obtains a weighted average F-measure of 0.77 on both validation and test set. Exploratory analysis of dataset is also carried out on the Factify data set and uncovers salient patterns and issues (e.g., word overlapping, visual entailment correlation, source bias) that motivates our hypothesis. Finally, we highlight challenges of the task and multimodal dataset for future research.
False claims that have been previously fact-checked can still spread on social media. To mitigate their continual spread, detecting previously fact-checked claims is indispensable. Given a claim, existing works focus on providing evidence for detection by reranking candidate fact-checking articles (FC-articles) retrieved by BM25. However, these performances may be limited because they ignore the following characteristics of FC-articles: (1) claims are often quoted to describe the checked events, providing lexical information besides semantics; (2) sentence templates to introduce or debunk claims are common across articles, providing pattern information. Models that ignore the two aspects only leverage semantic relevance and may be misled by sentences that describe similar but irrelevant events. In this paper, we propose a novel reranker, MTM (Memory-enhanced Transformers for Matching) to rank FC-articles using key sentences selected with event (lexical and semantic) and pattern information. For event information, we propose a ROUGE-guided Transformer which is finetuned with regression of ROUGE. For pattern information, we generate pattern vectors for matching with sentences. By fusing event and pattern information, we select key sentences to represent an article and then predict if the article fact-checks the given claim using the claim, key sentences, and patterns. Experiments on two real-world datasets show that MTM outperforms existing methods. Human evaluation proves that MTM can capture key sentences for explanations. The code and the dataset are at https://github.com/ICTMCG/MTM.
Recently, information retrieval has seen the emergence of dense retrievers, using neural networks, as an alternative to classical sparse methods based on term-frequency. These models have obtained state-of-the-art results on datasets and tasks where large training sets are available. However, they do not transfer well to new applications with no training data, and are outperformed by unsupervised term-frequency methods such as BM25. In this work, we explore the limits of contrastive learning as a way to train unsupervised dense retrievers and show that it leads to strong performance in various retrieval settings. On the BEIR benchmark our unsupervised model outperforms BM25 on 11 out of 15 datasets for the Recall@100. When used as pre-training before fine-tuning, either on a few thousands in-domain examples or on the large MS~MARCO dataset, our contrastive model leads to improvements on the BEIR benchmark. Finally, we evaluate our approach for multi-lingual retrieval, where training data is even scarcer than for English, and show that our approach leads to strong unsupervised performance. Our model also exhibits strong cross-lingual transfer when fine-tuned on supervised English data only and evaluated on low resources language such as Swahili. We show that our unsupervised models can perform cross-lingual retrieval between different scripts, such as retrieving English documents from Arabic queries, which would not be possible with term matching methods.
Accurate evidence retrieval is essential for automated fact checking. Little previous research has focused on the differences between true and false claims and how they affect evidence retrieval. This paper shows that, compared with true claims, false claims more frequently contain irrelevant entities which can distract evidence retrieval model. A BERT-based retrieval model made more mistakes in retrieving refuting evidence for false claims than supporting evidence for true claims. When tested with adversarial false claims (synthetically generated) containing irrelevant entities, the recall of the retrieval model is significantly lower than that for original claims. These results suggest that the vanilla BERT-based retrieval model is not robust to irrelevant entities in the false claims. By augmenting the training data with synthetic false claims containing irrelevant entities, the trained model achieved higher evidence recall, including that of false claims with irrelevant entities. In addition, using separate models to retrieve refuting and supporting evidence and then aggregating them can also increase the evidence recall, including that of false claims with irrelevant entities. These results suggest that we can increase the BERT-based retrieval model's robustness to false claims with irrelevant entities via data augmentation and model ensemble.
Fact-checking systems have become important tools to verify fake and misguiding news. These systems become more trustworthy when human-readable explanations accompany the veracity labels. However, manual collection of such explanations is expensive and time-consuming. Recent works frame explanation generation as extractive summarization, and propose to automatically select a sufficient subset of the most important facts from the ruling comments (RCs) of a professional journalist to obtain fact-checking explanations. However, these explanations lack fluency and sentence coherence. In this work, we present an iterative edit-based algorithm that uses only phrase-level edits to perform unsupervised post-editing of disconnected RCs. To regulate our editing algorithm, we use a scoring function with components including fluency and semantic preservation. In addition, we show the applicability of our approach in a completely unsupervised setting. We experiment with two benchmark datasets, LIAR-PLUS and PubHealth. We show that our model generates explanations that are fluent, readable, non-redundant, and cover important information for the fact check.
Visual graphics, such as plots, charts, and figures, are widely used to communicate statistical conclusions. Extracting information directly from such visualizations is a key sub-problem for effective search through scientific corpora, fact-checking, and data extraction. This paper presents a framework for automatically extracting compared variables from statistical charts. Due to the diversity and variation of charting styles, libraries, and tools, we leverage a computer vision based framework to automatically identify and localize visualization facets in line graphs, scatter plots, or bar graphs and can include multiple series per graph. The framework is trained on a large synthetically generated corpus of matplotlib charts and we evaluate the trained model on other chart datasets. In controlled experiments, our framework is able to classify, with 87.5% accuracy, the correlation between variables for graphs with 1-3 series per graph, varying colors, and solid line styles. When deployed on real-world graphs scraped from the internet, it achieves 72.8% accuracy (81.2% accuracy when excluding "hard" graphs). When deployed on the FigureQA dataset, it achieves 84.7% accuracy.
The scientific claim verification task requires an NLP system to label scientific documents which Support or Refute an input claim, and to select evidentiary sentences (or rationales) justifying each predicted label. In this work, we present MultiVerS, which predicts a fact-checking label and identifies rationales in a multitask fashion based on a shared encoding of the claim and full document context. This approach accomplishes two key modeling goals. First, it ensures that all relevant contextual information is incorporated into each labeling decision. Second, it enables the model to learn from instances annotated with a document-level fact-checking label, but lacking sentence-level rationales. This allows MultiVerS to perform weakly-supervised domain adaptation by training on scientific documents labeled using high-precision heuristics. Our approach outperforms two competitive baselines on three scientific claim verification datasets, with particularly strong performance in zero / few-shot domain adaptation experiments. Our code and data are available at https://github.com/dwadden/multivers.
Misinformation is now a major problem due to its potential high risks to our core democratic and societal values and orders. Out-of-context misinformation is one of the easiest and effective ways used by adversaries to spread viral false stories. In this threat, a real image is re-purposed to support other narratives by misrepresenting its context and/or elements. The internet is being used as the go-to way to verify information using different sources and modalities. Our goal is an inspectable method that automates this time-consuming and reasoning-intensive process by fact-checking the image-caption pairing using Web evidence. To integrate evidence and cues from both modalities, we introduce the concept of 'multi-modal cycle-consistency check'; starting from the image/caption, we gather textual/visual evidence, which will be compared against the other paired caption/image, respectively. Moreover, we propose a novel architecture, Consistency-Checking Network (CCN), that mimics the layered human reasoning across the same and different modalities: the caption vs. textual evidence, the image vs. visual evidence, and the image vs. caption. Our work offers the first step and benchmark for open-domain, content-based, multi-modal fact-checking, and significantly outperforms previous baselines that did not leverage external evidence.
While Wikipedia has been utilized for fact-checking and claim verification to debunk misinformation and disinformation, it is essential to either improve article quality and rule out noisy articles. Self-contradiction is one of the low-quality article types in Wikipedia. In this work, we propose a task of detecting self-contradiction articles in Wikipedia. Based on the "self-contradictory" template, we create a novel dataset for the self-contradiction detection task. Conventional contradiction detection focuses on comparing pairs of sentences or claims, but self-contradiction detection needs to further reason the semantics of an article and simultaneously learn the contradiction-aware comparison from all pairs of sentences. Therefore, we present the first model, Pairwise Contradiction Neural Network (PCNN), to not only effectively identify self-contradiction articles, but also highlight the most contradiction pairs of contradiction sentences. The main idea of PCNN is two-fold. First, to mitigate the effect of data scarcity on self-contradiction articles, we pre-train the module of pairwise contradiction learning using SNLI and MNLI benchmarks. Second, we select top-K sentence pairs with the highest contradiction probability values and model their correlation to determine whether the corresponding article belongs to self-contradiction. Experiments conducted on the proposed WikiContradiction dataset exhibit that PCNN can generate promising performance and comprehensively highlight the sentence pairs the contradiction locates.
While recent work on automated fact-checking has focused mainly on verifying and explaining claims, for which the list of claims is readily available, identifying check-worthy claim sentences from a text remains challenging. Current claim identification models rely on manual annotations for each sentence in the text, which is an expensive task and challenging to conduct on a frequent basis across multiple domains. This paper explores methodology to identify check-worthy claim sentences from fake news articles, irrespective of domain, without explicit sentence-level annotations. We leverage two internal supervisory signals - headline and the abstractive summary - to rank the sentences based on semantic similarity. We hypothesize that this ranking directly correlates to the check-worthiness of the sentences. To assess the effectiveness of this hypothesis, we build pipelines that leverage the ranking of sentences based on either the headline or the abstractive summary. The top-ranked sentences are used for the downstream fact-checking tasks of evidence retrieval and the article's veracity prediction by the pipeline. Our findings suggest that the top 3 ranked sentences contain enough information for evidence-based fact-checking of a fake news article. We also show that while the headline has more gisting similarity with how a fact-checking website writes a claim, the summary-based pipeline is the most promising for an end-to-end fact-checking system.
Our society produces and shares overwhelming amounts of information through Online Social Networks (OSNs). Within this environment, misinformation and disinformation have proliferated, becoming a public safety concern in most countries. Allowing the public and professionals to efficiently find reliable evidences about the factual veracity of a claim is a crucial step to mitigate this harmful spread. To this end, we propose FacTeR-Check, a multilingual architecture for semi-automated fact-checking that can be used for either applications designed for the general public and by fact-checking organisations. FacTeR-Check enables retrieving fact-checked information, unchecked claims verification and tracking dangerous information over social media. This architectures involves several modules developed to evaluate semantic similarity, to calculate natural language inference and to retrieve information from Online Social Networks. The union of all these components builds a semi-automated fact-checking tool able of verifying new claims, to extract related evidence, and to track the evolution of a hoax on a OSN. While individual modules are validated on related benchmarks (mainly MSTS and SICK), the complete architecture is validated using a new dataset called NLI19-SP that is publicly released with COVID-19 related hoaxes and tweets from Spanish social media. Our results show state-of-the-art performance on the individual benchmarks, as well as producing a useful analysis of the evolution over time of 61 different hoaxes.
Over the recent years, large pretrained language models (LM) have revolutionized the field of natural language processing (NLP). However, while pretraining on general language has been shown to work very well for common language, it has been observed that niche language poses problems. In particular, climate-related texts include specific language that common LMs can not represent accurately. We argue that this shortcoming of today's LMs limits the applicability of modern NLP to the broad field of text processing of climate-related texts. As a remedy, we propose CLIMATEBERT, a transformer-based language model that is further pretrained on over 2 million paragraphs of climate-related texts, crawled from various sources such as common news, research articles, and climate reporting of companies. We find that CLIMATEBERT leads to a 48% improvement on a masked language model objective which, in turn, leads to lowering error rates by 3.57% to 35.71% for various climate-related downstream tasks like text classification, sentiment analysis, and fact-checking.
This paper describes SciClops, a method to help combat online scientific misinformation. Although automated fact-checking methods have gained significant attention recently, they require pre-existing ground-truth evidence, which, in the scientific context, is sparse and scattered across a constantly-evolving scientific literature. Existing methods do not exploit this literature, which can effectively contextualize and combat science-related fallacies. Furthermore, these methods rarely require human intervention, which is essential for the convoluted and critical domain of scientific misinformation. SciClops involves three main steps to process scientific claims found in online news articles and social media postings: extraction, clustering, and contextualization. First, the extraction of scientific claims takes place using a domain-specific, fine-tuned transformer model. Second, similar claims extracted from heterogeneous sources are clustered together with related scientific literature using a method that exploits their content and the connections among them. Third, check-worthy claims, broadcasted by popular yet unreliable sources, are highlighted together with an enhanced fact-checking context that includes related verified claims, news articles, and scientific papers. Extensive experiments show that SciClops tackles sufficiently these three steps, and effectively assists non-expert fact-checkers in the verification of complex scientific claims, outperforming commercial fact-checking systems.
Fact-checking on the Web has become the main mechanism through which we detect the credibility of the news or information. Existing fact-checkers verify the authenticity of the information (support or refute the claim) based on secondary sources of information. However, existing approaches do not consider the problem of model updates due to constantly increasing training data due to user feedback. It is therefore important to conduct user studies to correct models' inference biases and improve the model in a life-long learning manner in the future according to the user feedback. In this paper, we present FaxPlainAC, a tool that gathers user feedback on the output of explainable fact-checking models. FaxPlainAC outputs both the model decision, i.e., whether the input fact is true or not, along with the supporting/refuting evidence considered by the model. Additionally, FaxPlainAC allows for accepting user feedback both on the prediction and explanation. Developed in Python, FaxPlainAC is designed as a modular and easily deployable tool. It can be integrated with other downstream tasks and allowing for fact-checking human annotation gathering and life-long learning.
Quotation extraction and attribution are challenging tasks, aiming at determining the spans containing quotations and attributing each quotation to the original speaker. Applying this task to news data is highly related to fact-checking, media monitoring and news tracking. Direct quotations are more traceable and informative, and therefore of great significance among different types of quotations. Therefore, this paper introduces DirectQuote, a corpus containing 19,760 paragraphs and 10,279 direct quotations manually annotated from online news media. To the best of our knowledge, this is the largest and most complete corpus that focuses on direct quotations in news texts. We ensure that each speaker in the annotation can be linked to a specific named entity on Wikidata, benefiting various downstream tasks. In addition, for the first time, we propose several sequence labeling models as baseline methods to extract and attribute quotations simultaneously in an end-to-end manner.
Fact-checking is an essential tool to mitigate the spread of misinformation and disinformation. We introduce the task of fact-checking in dialogue, which is a relatively unexplored area. We construct DialFact, a testing benchmark dataset of 22,245 annotated conversational claims, paired with pieces of evidence from Wikipedia. There are three sub-tasks in DialFact: 1) Verifiable claim detection task distinguishes whether a response carries verifiable factual information; 2) Evidence retrieval task retrieves the most relevant Wikipedia snippets as evidence; 3) Claim verification task predicts a dialogue response to be supported, refuted, or not enough information. We found that existing fact-checking models trained on non-dialogue data like FEVER fail to perform well on our task, and thus, we propose a simple yet data-efficient solution to effectively improve fact-checking performance in dialogue. We point out unique challenges in DialFact such as handling the colloquialisms, coreferences and retrieval ambiguities in the error analysis to shed light on future research in this direction.